Stokastik

Machine Learning, AI and Programming

Tag: Graph Processing

Designing a Contextual Graphical Model for Words

I have been reading about Word Embedding methods that encode words found in text documents into multi-dimensional vectors. The purpose of encoding into¬†vectors is to give "meaning" to words or phrases¬†in a context. Traditional methods of document classification treat each word in isolation or at-most use a N-gram approach i.e. in vector space, the words are represented as one-hot vectors which are sparse and do not convey any meaning whereas […]

Continue Reading →